Google DeepMind's repositories
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
mujoco_menagerie
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
android_env
RL research on Android devices.
mujoco_mpc
Real-time behaviour synthesis with MuJoCo, using Predictive Control
meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
long-form-factuality
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
neural_networks_solomonoff_induction
Learning Universal Predictors
nuclease_design
ML-guided enzyme engineering
multiscope
Real-time visualisation